Investigating the Effect of Mode Assignment on the Response Rate in the Current Population Survey

• Activity Number: 68
• Type: Topic Contributed
• Date/Time: Sunday, August 9, 2015 : 4:00 PM to 5:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Polly Phipps* and Daniel Yang and Brian Meekins and Daniell Toth
• Companies: Bureau of Labor Statistics and Bureau of Labor Statistics and Bureau of Labor Statistics and Bureau of Labor Statistics
• Keywords: nonresponse ; panel survey ; data collection mode ; computer-assisted telephone interview ; paradata ; propensity models

Abstract

The Current Population Survey (CPS) is a rotating monthly panel survey of households that provides comprehensive information on the U.S. labor force. The collection mode of the CPS is either by personal visit or telephone interview. In this study, we focus on data collection during the first four months of household participation in the eight-month survey. The first month's visit is conducted by a Census field representative (FR), most commonly using computer-assisted personal interviewing (CAPI). Over the next three months, some household's data may continue to be collected by the FR either in-person or over the telephone, while other households are transferred to a centralized telephone call center for collection by computer-assisted telephone interview (CATI). Assignment to CATI is based on a number of criteria determined by the FR, the Census regional office, and outcomes from the previous month. In this study, we examine which demographic variables and outcomes are associated with the CATI assignment propensity. In addition, we investigate which variables are associated with the propensity of success in CATI.